I am at lesson 3 and attempting to re-write Vgg16 from scratch (or pseudo-scratch, atleast) and I am stumped by the use of ‘.N’ notation as in:
def fit_model(model, batches, val_batches, nb_epoch=1):
model.fit_generator(batches, samples_per_epoch=batches.N, nb_epoch=nb_epoch,
validation_data=val_batches, nb_val_samples=val_batches.N)
My best guess is that its related to the the ‘MixIterator’ class in the provided utils. It seems to be used to provide a numpy array with an attribute N that matches the number of batches in a dataset but I can’t seem to fully comprehend what is going on with the code. Any tips? Thanks